Search

Sentiment analysis is an automated approach which is utilized in process of analysing textual data to describe public opinion. The sentiment analysis has major role in creating impact in the day‐to‐day life of individuals. However, a precise interpretation of text still relies as a major concern in classifying sentiment. So, this research introduced Bidirectional Long Short Term Memory with Ranger AdaBelief Optimizer (Bi‐LSTM RAO) to classify sentiment of tweets. Initially, data is obtained from Twitter API, Sentiment 140 and Stanford Sentiment Treebank‐2 (SST‐2). The raw data is pre‐processed and it is subjected to feature extraction which is performed using Bag of Words (BoW) and Term Frequency‐Inverse Document Frequency (TF‐IDF). The feature selection is performed using Gazelle Optimization Algorithm (GOA) which removes the irrelevant or redundant features that maximized model performance and classification is performed using Bi LSTM–RAO. The RAO optimizes the loss function of Bi‐LSTM model that maximized accuracy. The classification accuracy of proposed method for Twitter API, Sentiment 140 and SST 2 dataset is obtained as 909.44%, 99.71% and 99.86%, respectively. These obtained results are comparably higher than ensemble framework, Robustly Optimized BERT and Gated Recurrent Unit (RoBERTa‐GRU), Logistic Regression‐Long Short Term Memory (LR‐LSTM), Convolutional Bi‐LSTM, Sentiment and Context Aware Attention‐based Hybrid Deep Neural Network (SCA‐HDNN) and Stochastic Gradient Descent optimization based Stochastic Gate Neural Network (SGD‐SGNN). [ABSTRACT FROM AUTHOR]

Service discovery is an inevitable process in most of the network. Mobile AdHoc network (MANET) being self-sustained and resource constrained, sharing of resources and service discovery is very essential. A service discovery protocol designed for a fixed network is not suitable for AdHoc network because of the constraint in the resources, mobility of nodes and the lack of centralized infrastructure. Therefore there arises a need to design protocols specific to MANET. A protocol designed for service discovery at the application layer in Mobile AdHoc Network would generate the same amount of control messages during service discovery as would a routing protocol during route discovery. To ease the network congestion it would be beneficial to integrate service discovery with route discovery. This would discover the services and route simultaneously. Therefore the AdHoc On-demand Distance Vector (AODV) routing protocol being a reactive routing protocol was modified to include service discovery so that as the services are discovered, a route to the service provider is also available. During service discovery if multiple servers are offering the same service, there arises a need to select the best one. We propose a ranking mechanism that selects an optimal server by considering the route and server specific metrics. We also propose an algorithm that performs service discovery by taking care of Expanding Ring Search of AODV protocol so as to be able to discover multiple servers. The proposed approach has been evaluated, and it was observed that the storage overhead is reduced by 50%, average Service Discovery Latency was reduced and the Service Discovery Ratio was improved by 16%. [ABSTRACT FROM AUTHOR]

The purpose of our study was to explore how people with epilepsy fared during two of the most stringent 4-month society-wide COVID-19-related pandemic restrictions in Ireland, in 2020 and one year later in 2021. This was in the context of their seizure control, lifestyle factors, and access to epilepsy-related healthcare services. A 14-part questionnaire was administered to adults with epilepsy during virtual specialist epilepsy clinics in a University Hospital in Dublin, Ireland at the end of the two lockdowns. People with epilepsy were questioned on their epilepsy control, lifestyle factors, and quality of epilepsy-related medical care, compared to pre-COVID times. The study sample consisted of two separate cohorts of those diagnosed with epilepsy (100 (51.8%) in 2020, and 93 (48.2%) in 2021, with similar baseline characteristics. There was no significant change in seizure control or lifestyle factors from 2020 to 2021, except for deterioration in anti-seizure medication (ASM) adherence in 2021 compared to 2020 (p = 0.028). There was no correlation between ASM adherence and other lifestyle factors. Over the two years, poor seizure control was significantly associated with poor sleep (p < 0.001) and average seizure frequency in a month (p = 0.007). We concluded that there was no significant difference between seizure control or lifestyle factors between the two most stringent lockdowns in Ireland, in 2020 and 2021. Furthermore, people with epilepsy reported that throughout the lockdowns access to services was well maintained, and they felt well supported by their services. Contrary to the popular opinion that COVID lockdowns greatly affected patients with chronic diseases, we found that those with epilepsy attending our service remained largely stable, optimistic, and healthy during this time. [ABSTRACT FROM AUTHOR]